Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Protein and ligand novelty in drug-target interaction prediction: a dual-encoder fusion strategy for more interpretable and generalizable modeling.

BMC bioinformatics·2026
Same author

Distinguishing Between Healthy and Unhealthy Newborns Based on Acoustic Features and Deep Learning Neural Networks Tuned by Bayesian Optimization and Random Search Algorithm.

Entropy (Basel, Switzerland)·2025
Same author

Generative AI with WGAN-GP for boosting seizure detection accuracy.

Frontiers in artificial intelligence·2024
Same author

Unveiling distinct kinematic profiles among total knee arthroplasty candidates through clustering technique.

Journal of orthopaedic surgery and research·2024
Same author

Domain adaptation for EEG-based, cross-subject epileptic seizure prediction.

Frontiers in neuroinformatics·2024
Same author

Use of psychoacoustic spectrum warping, decision template fusion, and neighborhood component analysis in newborn cry diagnostic systems.

The Journal of the Acoustical Society of America·2024

Related Experiment Video

Updated: Mar 16, 2026

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.4K

Cry-based infant pathology classification using GMMs.

Hesam Farsaie Alaie1, Lina Abou-Abbas1, Chakib Tadj1

  • 1MMS Lab, Department of Electrical Engineering, École de Technologie Supérieure, Université du Québec, 1100 rue Notre-Dame Ouest, Montréal, QC, Canada, H3C 1K3.

Speech Communication
|August 16, 2016
PubMed
Summary

This study presents a novel noninvasive healthcare system for diagnosing infant health using acoustic analysis of cry signals. The system accurately classifies healthy and sick newborns based on cry characteristics, outperforming traditional methods.

Keywords:
Expiratory and inspiratory cryGaussian mixture modelLikelihood ratio scoresMel-frequency Cepstral CoefficientNewborn infant criesUniversal background model

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.6K
Flow Cytometry and Single-Cell Analysis for Characterizing Microglia Activation in Early Postnatal Mouse Brain Development
09:48

Flow Cytometry and Single-Cell Analysis for Characterizing Microglia Activation in Early Postnatal Mouse Brain Development

Published on: October 3, 2025

1.0K

Related Experiment Videos

Last Updated: Mar 16, 2026

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.4K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.6K
Flow Cytometry and Single-Cell Analysis for Characterizing Microglia Activation in Early Postnatal Mouse Brain Development
09:48

Flow Cytometry and Single-Cell Analysis for Characterizing Microglia Activation in Early Postnatal Mouse Brain Development

Published on: October 3, 2025

1.0K

Area of Science:

  • Biomedical Engineering
  • Infant Health Monitoring
  • Acoustic Signal Processing

Background:

  • Traditional infant cry analysis often overlooks pathological conditions.
  • Noninvasive diagnostic methods for newborns are crucial for early detection and intervention.
  • Accurate classification of infant health solely through cry signals remains a challenge.

Purpose of the Study:

  • To develop a noninvasive healthcare system for classifying healthy and sick newborns using acoustic analysis of cry signals.
  • To quantitatively extract and measure cry characteristics from noisy infant cries.
  • To introduce a novel method for cry pattern analysis and classification.

Main Methods:

  • Extraction of static and dynamic Mel-Frequency Cepstral Coefficients (MFCCs) from expiratory and inspiratory cry vocalizations.
  • Application of the Boosting Mixture Learning (BML) method for deriving healthy and pathology subclass models from Gaussian Mixture Model-Universal Background Model (GMM-UBM).
  • Implementation of a hierarchical classification scheme with score-level fusion of expiratory and inspiratory cry subsystems within the newborn cry-based diagnostic system (NCDS).

Main Results:

  • The developed system successfully classifies healthy and sick newborns based on cry characteristics.
  • The adapted BML method demonstrated lower error rates compared to Bayesian and Maximum a Posteriori (MAP) adaptation approaches.
  • The acoustic analysis effectively extracted discriminative features from noisy infant cries.

Conclusions:

  • The proposed newborn cry-based diagnostic system (NCDS) offers a reliable, noninvasive method for infant health assessment.
  • The BML method shows significant promise for improving the accuracy of cry-based infant diagnostics.
  • Quantitative acoustic analysis of infant cries can serve as an effective tool for distinguishing between healthy and sick newborns.